Semi-supervised Deep Large-Baseline Homography Estimation with Progressive Equivalence Constraint
Hai Jiang, Haipeng Li, Yuhang Lu, Songchen Han, Shuaicheng Liu
Abstract
Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field. To address it, we propose a progressive estimation strategy by converting large-baseline homography into multiple intermediate ones, cumulatively multiplying these intermediate items can reconstruct the initial homography. Meanwhile, a semi-supervised homography identity loss, which consists of two components: a supervised objective and an unsupervised objective, is introduced. The first supervised loss is acting to optimize intermediate homographies, while the second unsupervised one helps to estimate a large-baseline homography without photometric losses. To validate our method, we propose a large-scale dataset that covers regular and challenging scenes. Experiments show that our method achieves state-of-the-art performance in large-baseline scenes while keeping competitive performance in small-baseline scenes. Code and dataset are available at https://github.com/megvii-research/LBHomo.
BibTeX
@article{Jiang_Li_Lu_Han_Liu_2023, title={Semi-supervised Deep Large-Baseline Homography Estimation with Progressive Equivalence Constraint}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25183}, DOI={10.1609/aaai.v37i1.25183}, abstractNote={Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field. To address it, we propose a progressive estimation strategy by converting large-baseline homography into multiple intermediate ones, cumulatively multiplying these intermediate items can reconstruct the initial homography. Meanwhile, a semi-supervised homography identity loss, which consists of two components: a supervised objective and an unsupervised objective, is introduced. The first supervised loss is acting to optimize intermediate homographies, while the second unsupervised one helps to estimate a large-baseline homography without photometric losses. To validate our method, we propose a large-scale dataset that covers regular and challenging scenes. Experiments show that our method achieves state-of-the-art performance in large-baseline scenes while keeping competitive performance in small-baseline scenes. Code and dataset are available at https://github.com/megvii-research/LBHomo.}, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Jiang, Hai and Li, Haipeng and Lu, Yuhang and Han, Songchen and Liu, Shuaicheng}, year={2023}, month={Jun.}, pages={1024-1032} }